{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/how-do-hyenas-deal-with-human-speech-speech","title":"How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena","arxiv_id":"2402.13208","date":"2024-02-20","proceeding":null,"authors":["Marco Gaido","Sara Papi","Matteo Negri","Luisa Bentivogli"],"abstract":"The attention mechanism, a cornerstone of state-of-the-art neural models, faces computational hurdles in processing long sequences due to its quadratic complexity. Consequently, research efforts in the last few years focused on finding more efficient alternatives. Among them, Hyena (Poli et al., 2023) stands out for achieving competitive results in both language modeling and image classification, while offering sub-quadratic memory and computational complexity. Building on these promising results, we propose ConfHyena, a Conformer whose encoder self-attentions are replaced with an adaptation of Hyena for speech processing, where the long input sequences cause high computational costs. Through experiments in automatic speech recognition (for English) and translation (from English into 8 target languages), we show that our best ConfHyena model significantly reduces the training time by 27%, at the cost of minimal quality degradation (~1%), which, in most cases, is not statistically significant.","url_abs":"https://arxiv.org/abs/2402.13208v1","url_pdf":"https://arxiv.org/pdf/2402.13208v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"how-do-hyenas-deal-with-human-speech-speech","repo_url":"https://github.com/hlt-mt/fbk-fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.13208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13208"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hlt-mt/fbk-fairseq","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"4d573553ce7d5023","entry":"Embedding","repo":"hlt-mt/fbk-fairseq","repo_kind":"official","path":"examples/speech_recognition/models/vggtransformer.py","file_url":"https://github.com/hlt-mt/fbk-fairseq/blob/HEAD/examples/speech_recognition/models/vggtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4d573553ce7d5023"}},{"code_sha256_prefix":"20ba2694765be3c9","entry":"prepare_transformer_decoder_params","repo":"hlt-mt/fbk-fairseq","repo_kind":"official","path":"examples/speech_recognition/models/vggtransformer.py","file_url":"https://github.com/hlt-mt/fbk-fairseq/blob/HEAD/examples/speech_recognition/models/vggtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"20ba2694765be3c9"}},{"code_sha256_prefix":"dbd845b65da5da61","entry":"prepare_transformer_encoder_params","repo":"hlt-mt/fbk-fairseq","repo_kind":"official","path":"examples/speech_recognition/models/vggtransformer.py","file_url":"https://github.com/hlt-mt/fbk-fairseq/blob/HEAD/examples/speech_recognition/models/vggtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dbd845b65da5da61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}